{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:28:12Z","timestamp":1743028092833,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030170646"},{"type":"electronic","value":"9783030170653"}],"license":[{"start":{"date-parts":[[2019,4,10]],"date-time":"2019-04-10T00:00:00Z","timestamp":1554854400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-17065-3_7","type":"book-chapter","created":{"date-parts":[[2019,4,9]],"date-time":"2019-04-09T01:38:22Z","timestamp":1554773902000},"page":"66-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving Audiovisual Content Annotation Through a Semi-automated Process Based on Deep Learning"],"prefix":"10.1007","author":[{"given":"Lu\u00eds","family":"Vila\u00e7a","sequence":"first","affiliation":[]},{"given":"Paula","family":"Viana","sequence":"additional","affiliation":[]},{"given":"Pedro","family":"Carvalho","sequence":"additional","affiliation":[]},{"given":"Teresa","family":"Andrade","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,10]]},"reference":[{"unstructured":"Darkflow repository. \n                  https:\/\/github.com\/thtrieu\/darkflow\n                  \n                . Accessed 09 July 2018","key":"7_CR1"},{"issue":"7","key":"7_CR2","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1109\/34.598228","volume":"19","author":"P.N. Belhumeur","year":"1997","unstructured":"Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. Technical report, Yale University, New Haven, United States (1997)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Bertini, M., Del\u00a0Bimbo, A., Torniai, C.: Automatic video annotation using ontologies extended with visual information. In: Proceedings of the 13th Annual ACM International Conference on Multimedia, MULTIMEDIA 2005, pp. 395\u2013398. ACM, New York (2005)","key":"7_CR3","DOI":"10.1145\/1101149.1101235"},{"issue":"6","key":"7_CR4","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"PAMI-8","author":"John Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(6), 679\u2013698 (1986)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection, vol. 1, pp. 886\u2013893, June 2005","key":"7_CR5"},{"doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","key":"7_CR6","DOI":"10.1109\/ICCV.2015.169"},{"doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR abs\/1311.2524 (2013)","key":"7_CR7","DOI":"10.1109\/CVPR.2014.81"},{"doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","key":"7_CR8","DOI":"10.1109\/ICCV.2017.322"},{"unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017)","key":"7_CR9"},{"issue":"3","key":"7_CR10","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/BF02311576","volume":"2","author":"AJ Howell","year":"1995","unstructured":"Howell, A.J., Buxton, H.: Invariance in radial basis function neural networks in human face classification. Neural Process. Lett. 2(3), 26\u201330 (1995)","journal-title":"Neural Process. Lett."},{"unstructured":"Kotropoulos, C., Pitas, I.: Rule-based face detection in frontal views. In: Proceedings International Conference on Acoustics, Speech and Signal Processing, vol. 4, pp. 2537\u20132540 (1997)","key":"7_CR11"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks, pp. 1097\u20131105 (2012)","key":"7_CR12"},{"issue":"7","key":"7_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/34.598231","volume":"19","author":"A Lanitis","year":"1997","unstructured":"Lanitis, A., Taylor, C.J., Cootes, T.F.: Automatic interpretation and coding of face images using flexible models. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 743\u2013756 (1997)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Larson, M., Soleymani, M., Serdyukov, P., Rudinac, S., Wartena, C., Murdock, V., Friedland, G., Ordelman, R., Jones, G.J.F.: Automatic tagging and geotagging in video collections and communities. In: Proceedings 1st ACM International Conference on Multimedia Retrieval, ICMR 2011, pp. 51:1\u201351:8. ACM, New York (2011)","key":"7_CR14","DOI":"10.1145\/1991996.1992047"},{"issue":"1","key":"7_CR15","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/72.554195","volume":"8","author":"S Lawrence","year":"1997","unstructured":"Lawrence, S., Giles, C.L., Tsoi, A.C., Back, A.D.: Face recognition: a convolutional neural-network approach. IEEE Trans. Neural Netw. 8(1), 98\u2013113 (1997)","journal-title":"IEEE Trans. Neural Netw."},{"doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","key":"7_CR16","DOI":"10.1007\/978-3-319-46448-0_2"},{"doi-asserted-by":"crossref","unstructured":"Moxley, E., Mei, T., Hua, X., Ma, W., Manjunath, B.S.: Automatic video annotation through search and mining. In: 2008 IEEE International Conference on Multimedia and Expo, pp. 685\u2013688, June 2008","key":"7_CR17","DOI":"10.1109\/ICME.2008.4607527"},{"unstructured":"Osuna, E., Freund, R., Girosit, F.: Training support vector machines: an application to face detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 130\u2013136, June 1997","key":"7_CR18"},{"doi-asserted-by":"crossref","unstructured":"Pinto, J.P., Viana, P.: TAG4VD: a game for collaborative video annotation. In: Proceedings of the 2013 ACM International Workshop on Immersive Media Experiences, ImmersiveMe 2013, pp. 25\u201328. ACM, New York (2013)","key":"7_CR19","DOI":"10.1145\/2512142.2512154"},{"doi-asserted-by":"crossref","unstructured":"Pinto, J.P., Viana, P.: Using the crowd to boost video annotation processes: a game based approach. In: Proceedings of the 12th European Conference on Visual Media Production, CVMP 2015, pp. 22:1\u201322:1. ACM, New York (2015)","key":"7_CR20","DOI":"10.1145\/2824840.2824853"},{"doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","key":"7_CR21","DOI":"10.1109\/CVPR.2016.91"},{"doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR abs\/1612.08242 (2016)","key":"7_CR22","DOI":"10.1109\/CVPR.2017.690"},{"unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks (2015)","key":"7_CR23"},{"unstructured":"Sirohey, S.A.: Human face segmentation and identification. Technical report (1993)","key":"7_CR24"},{"issue":"3","key":"7_CR25","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1364\/JOSAA.4.000519","volume":"4","author":"L Sirovich","year":"1987","unstructured":"Sirovich, L., Kirby, M.: Low-dimensional procedure for the characterization of human faces. J. Opt. Soc. Am. A 4(3), 519\u2013524 (1987)","journal-title":"J. Opt. Soc. Am. A"},{"doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. CoRR abs\/1512.00567 (2015)","key":"7_CR26","DOI":"10.1109\/CVPR.2016.308"},{"unstructured":"Tsukamoto, A., Lee, C.W., Tsuji, S.: Detection and pose estimation of human face with synthesized image models. In: Proceedings of 12th International Conference on Pattern Recognition, vol. 1, pp. 754\u2013757, October 1994","key":"7_CR27"},{"unstructured":"Tukamoto, A.: Detection and tracking of human face with synthesized templates. In: Proceedings of the ACCV 1993, pp. 183\u2013186 (1993)","key":"7_CR28"},{"key":"7_CR29","volume-title":"The Nature of Statistical Learning Theory","author":"V Vapnik","year":"2013","unstructured":"Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (2013)"},{"issue":"1","key":"7_CR30","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13673-017-0094-5","volume":"7","author":"P Viana","year":"2017","unstructured":"Viana, P., Pinto, J.P.: A collaborative approach for semantic time-based video annotation using gamification. Hum.-Centric Comput. Inf. Sci. 7(1), 13 (2017)","journal-title":"Hum.-Centric Comput. Inf. Sci."},{"unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features, vol. 1, pp. I-511\u2013I-518 (2001)","key":"7_CR31"},{"issue":"1","key":"7_CR32","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0031-3203(94)90017-5","volume":"27","author":"G Yang","year":"1994","unstructured":"Yang, G., Huang, T.S.: Human face detection in a complex background. Pattern Recognit. 27(1), 53\u201363 (1994)","journal-title":"Pattern Recognit."},{"unstructured":"Yang, M.H., Ahuja, N.: Detecting human faces in color images. In: Proceedings of the International Conference on Image Processing, ICIP 1998, vol. 1, pp. 127\u2013130, October 1998","key":"7_CR33"}],"container-title":["Advances in Intelligent Systems and Computing","Proceedings of the Tenth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2018)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-17065-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,18]],"date-time":"2019-05-18T04:10:25Z","timestamp":1558152625000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-17065-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,10]]},"ISBN":["9783030170646","9783030170653"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-17065-3_7","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2019,4,10]]},"assertion":[{"value":"10 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SoCPaR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Soft Computing and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socpar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mirlabs.net\/socpar18\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}